© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 16338
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to healthcare services and clinical partnerships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    after "than."

    np_acts-logits-general · gemini-2.0-flash

    methods to, algorithms than, arrangement composed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     anything
    -0.61
     terakhir
    -0.60
     every
    -0.60
     оригіналу
    -0.59
    每一个
    -0.56
    czegó
    -0.56
     définiti
    -0.55
    Anything
    -0.55
     everything
    -0.54
    ngilizce
    -0.54
    POSITIVE LOGITS
     similarly
    1.06
     similar
    0.91
     equally
    0.85
     igualmente
    0.81
     besides
    0.80
    similar
    0.79
     unrelated
    0.78
     than
    0.78
    同様
    0.77
     serupa
    0.77
    Activations Density 0.424%

    No Known Activations